Upgrade GFPGAN to Version 1.4

docker-build/Dockerfile

@@ -47,7 +47,7 @@ RUN         git clone https://github.com/TencentARC/GFPGAN.git
 WORKDIR     /GFPGAN 
 RUN         pip3 install -r requirements.txt \
             && python3 setup.py develop \
-            && ln -s "/data/GFPGANv1.3.pth" experiments/pretrained_models/GFPGANv1.3.pth
+            && ln -s "/data/GFPGANv1.4.pth" experiments/pretrained_models/GFPGANv1.4.pth
 
 WORKDIR     /stable-diffusion 
 RUN         python3 scripts/preload_models.py         

docs/features/CLI.md

@@ -8,20 +8,23 @@ hide:
 
 ## **Interactive Command Line Interface**
 
-The `dream.py` script, located in `scripts/dream.py`, provides an interactive interface to image
+The `dream.py` script, located in `scripts/dream.py`, provides an interactive
-generation similar to the "dream mothership" bot that Stable AI provided on its Discord server.
+interface to image generation similar to the "dream mothership" bot that Stable
+AI provided on its Discord server.
 
 Unlike the `txt2img.py` and `img2img.py` scripts provided in the original
-[CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion) source code repository, the
+[CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion) source
-time-consuming initialization of the AI model initialization only happens once. After that image
+code repository, the time-consuming initialization of the AI model
-generation from the command-line interface is very fast.
+initialization only happens once. After that image generation from the
+command-line interface is very fast.
 
-The script uses the readline library to allow for in-line editing, command history (++up++ and
+The script uses the readline library to allow for in-line editing, command
-++down++), autocompletion, and more. To help keep track of which prompts generated which images, the
+history (++up++ and ++down++), autocompletion, and more. To help keep track of
-script writes a log file of image names and prompts to the selected output directory.
+which prompts generated which images, the script writes a log file of image
+names and prompts to the selected output directory.
 
-In addition, as of version 1.02, it also writes the prompt into the PNG file's metadata where it can
+In addition, as of version 1.02, it also writes the prompt into the PNG file's
-be retrieved using `scripts/images2prompt.py`
+metadata where it can be retrieved using `scripts/images2prompt.py`
 
 The script is confirmed to work on Linux, Windows and Mac systems.
 
@@ -56,21 +59,24 @@ dream> q
 
 ![dream-py-demo](../assets/dream-py-demo.png)
 
-The `dream>` prompt's arguments are pretty much identical to those used in the Discord bot, except
+The `dream>` prompt's arguments are pretty much identical to those used in the
-you don't need to type "!dream" (it doesn't hurt if you do). A significant change is that creation
+Discord bot, except you don't need to type "!dream" (it doesn't hurt if you do).
-of individual images is now the default unless `--grid` (`-g`) is given. A full list is given in
+A significant change is that creation of individual images is now the default
+unless `--grid` (`-g`) is given. A full list is given in
 [List of prompt arguments](#list-of-prompt-arguments).
 
 ## Arguments
 
-The script itself also recognizes a series of command-line switches that will change important
+The script itself also recognizes a series of command-line switches that will
-global defaults, such as the directory for image outputs and the location of the model weight files.
+change important global defaults, such as the directory for image outputs and
+the location of the model weight files.
 
 ### List of arguments recognized at the command line
 
-These command-line arguments can be passed to `dream.py` when you first run it from the Windows, Mac
+These command-line arguments can be passed to `dream.py` when you first run it
-or Linux command line. Some set defaults that can be overridden on a per-prompt basis (see [List of
+from the Windows, Mac or Linux command line. Some set defaults that can be
-prompt arguments] (#list-of-prompt-arguments). Others
+overridden on a per-prompt basis (see [List of prompt arguments]
+(#list-of-prompt-arguments). Others
 
 | Argument <img width="240" align="right"/> | Shortcut <img width="100" align="right"/> | Default <img width="320" align="right"/>       | Description                                                                                          |
 | ----------------------------------------- | ----------------------------------------- | ---------------------------------------------- | ---------------------------------------------------------------------------------------------------- |
@@ -90,7 +96,7 @@ prompt arguments] (#list-of-prompt-arguments). Others
 | `--seamless`                              |                                           | `False`                                        | Create interesting effects by tiling elements of the image.                                          |
 | `--embedding_path <path>`                 |                                           | `None`                                         | Path to pre-trained embedding manager checkpoints, for custom models                                 |
 | `--gfpgan_dir`                            |                                           | `src/gfpgan`                                   | Path to where GFPGAN is installed.                                                                   |
-| `--gfpgan_model_path`                     |                                           | `experiments/pretrained_models/GFPGANv1.3.pth` | Path to GFPGAN model file, relative to `--gfpgan_dir`.                                               |
+| `--gfpgan_model_path`                     |                                           | `experiments/pretrained_models/GFPGANv1.4.pth` | Path to GFPGAN model file, relative to `--gfpgan_dir`.                                               |
 | `--device <device>`                       | `-d<device>`                              | `torch.cuda.current_device()`                  | Device to run SD on, e.g. "cuda:0"                                                                   |
 
 #### deprecated
@@ -115,9 +121,10 @@ These arguments are deprecated but still work:
 
 ### List of prompt arguments
 
-After the `dream.py` script initializes, it will present you with a **`dream>`** prompt. Here you
+After the `dream.py` script initializes, it will present you with a **`dream>`**
-can enter information to generate images from text (txt2img), to embellish an existing image or
+prompt. Here you can enter information to generate images from text (txt2img),
-sketch (img2img), or to selectively alter chosen regions of the image (inpainting).
+to embellish an existing image or sketch (img2img), or to selectively alter
+chosen regions of the image (inpainting).
 
 #### txt2img
 
@@ -171,12 +178,13 @@ Those are the `dream` commands that apply to txt2img:
     than 640x480. Otherwise the image size will be identical to the provided photo and you may run out
     of memory if it is large.
 
-Repeated chaining of img2img on an image can result in significant color shifts in the output,
+Repeated chaining of img2img on an image can result in significant color shifts
-especially if run with lower strength. Color correction can be run against a reference image to fix
+in the output, especially if run with lower strength. Color correction can be
-this issue. Use the original input image to the chain as the the reference image for each step in
+run against a reference image to fix this issue. Use the original input image to
-the chain.
+the chain as the the reference image for each step in the chain.
 
-In addition to the command-line options recognized by txt2img, img2img accepts additional options:
+In addition to the command-line options recognized by txt2img, img2img accepts
+additional options:
 
 | Argument <img width="160" align="right"/> | Shortcut    | Default | Description                                                                                                                                |
 | ----------------------------------------- | ----------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
@@ -198,8 +206,8 @@ In addition to the command-line options recognized by txt2img, img2img accepts a
     the areas to overpaint made transparent, but you must be careful not to destroy the pixels
     underneath when you create the transparent areas. See [Inpainting](./INPAINTING.md) for details.
 
-Inpainting accepts all the arguments used for txt2img and img2img, as well as the `--mask` (`-M`)
+Inpainting accepts all the arguments used for txt2img and img2img, as well as
-argument:
+the `--mask` (`-M`) argument:
 
 | Argument <img width="100" align="right"/> | Shortcut   | Default | Description                                                                                      |
 | ----------------------------------------- | ---------- | ------- | ------------------------------------------------------------------------------------------------ |
@@ -207,37 +215,42 @@ argument:
 
 ## Command-line editing and completion
 
-If you are on a Macintosh or Linux machine, the command-line offers convenient history tracking,
+If you are on a Macintosh or Linux machine, the command-line offers convenient
-editing, and command completion.
+history tracking, editing, and command completion.
 
-- To scroll through previous commands and potentially edit/reuse them, use the ++up++ and ++down++
+- To scroll through previous commands and potentially edit/reuse them, use the
-  cursor keys.
+  ++up++ and ++down++ cursor keys.
-- To edit the current command, use the ++left++ and ++right++ cursor keys to position the cursor,
+- To edit the current command, use the ++left++ and ++right++ cursor keys to
-  and then ++backspace++, ++delete++ or ++insert++ characters.
+  position the cursor, and then ++backspace++, ++delete++ or ++insert++
-- To move to the very beginning of the command, type ++ctrl+a++ (or ++command+a++ on the Mac)
+  characters.
+- To move to the very beginning of the command, type ++ctrl+a++ (or
+  ++command+a++ on the Mac)
 - To move to the end of the command, type ++ctrl+e++.
-- To cut a section of the command, position the cursor where you want to start cutting and type
+- To cut a section of the command, position the cursor where you want to start
-  ++ctrl+k++.
+  cutting and type ++ctrl+k++.
-- To paste a cut section back in, position the cursor where you want to paste, and type ++ctrl+y++
+- To paste a cut section back in, position the cursor where you want to paste,
+  and type ++ctrl+y++
 
-Windows users can get similar, but more limited, functionality if they launch `dream.py` with the
+Windows users can get similar, but more limited, functionality if they launch
-"winpty" program:
+`dream.py` with the "winpty" program:
 
 ```batch
 winpty python scripts\dream.py
 ```
 
-On the Mac and Linux platforms, when you exit `dream.py`, the last 1000 lines of your command-line
+On the Mac and Linux platforms, when you exit `dream.py`, the last 1000 lines of
-history will be saved. When you restart `dream.py`, you can access the saved history using the
+your command-line history will be saved. When you restart `dream.py`, you can
-++up++ key.
+access the saved history using the ++up++ key.
 
-In addition, limited command-line completion is installed. In various contexts, you can start typing
+In addition, limited command-line completion is installed. In various contexts,
-your command and press tab. A list of potential completions will be presented to you. You can then
+you can start typing your command and press tab. A list of potential completions
-type a little more, hit tab again, and eventually autocomplete what you want.
+will be presented to you. You can then type a little more, hit tab again, and
+eventually autocomplete what you want.
 
-When specifying file paths using the one-letter shortcuts, the CLI will attempt to complete
+When specifying file paths using the one-letter shortcuts, the CLI will attempt
-pathnames for you. This is most handy for the `-I` (init image) and `-M` (init mask) paths. To
+to complete pathnames for you. This is most handy for the `-I` (init image) and
-initiate completion, start the path with a slash `/` or `./`, for example:
+`-M` (init mask) paths. To initiate completion, start the path with a slash `/`
+or `./`, for example:
 
 ```bash
 dream> "zebra with a mustache" -I./test-pictures<TAB>

docs/features/UPSCALE.md

@@ -4,37 +4,42 @@ title: Upscale
 
 ## Intro
 
-The script provides the ability to restore faces and upscale. You can apply these operations
+The script provides the ability to restore faces and upscale. You can apply
-at the time you generate the images, or at any time to a previously-generated PNG file, using 
+these operations at the time you generate the images, or at any time to a
-the [!fix](#fixing-previously-generated-images) command.
+previously-generated PNG file, using the
+[!fix](#fixing-previously-generated-images) command.
 
 ## Face Fixing
 
-The default face restoration module is GFPGAN. The default upscale is Real-ESRGAN. For an alternative
+The default face restoration module is GFPGAN. The default upscale is
-face restoration module, see [CodeFormer Support] below.
+Real-ESRGAN. For an alternative face restoration module, see [CodeFormer
+Support] below.
 
-As of version 1.14, environment.yaml will install the Real-ESRGAN package into the standard install
+As of version 1.14, environment.yaml will install the Real-ESRGAN package into
-location for python packages, and will put GFPGAN into a subdirectory of "src" in the
+the standard install location for python packages, and will put GFPGAN into a
-stable-diffusion directory. (The reason for this is that the standard GFPGAN distribution has a
+subdirectory of "src" in the stable-diffusion directory. (The reason for this is
-minor bug that adversely affects image color.) Upscaling with Real-ESRGAN should "just work" without
+that the standard GFPGAN distribution has a minor bug that adversely affects
-further intervention. Simply pass the --upscale (-U) option on the dream> command line, or indicate
+image color.) Upscaling with Real-ESRGAN should "just work" without further
-the desired scale on the popup in the Web GUI.
+intervention. Simply pass the --upscale (-U) option on the dream> command line,
+or indicate the desired scale on the popup in the Web GUI.
 
-For **GFPGAN** to work, there is one additional step needed. You will need to download and copy the
+For **GFPGAN** to work, there is one additional step needed. You will need to
-GFPGAN [models file](https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth)
+download and copy the GFPGAN
-into **src/gfpgan/experiments/pretrained_models**. On Mac and Linux systems, here's how you'd do it
+[models file](https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth)
-using **wget**:
+into **src/gfpgan/experiments/pretrained_models**. On Mac and Linux systems,
+here's how you'd do it using **wget**:
 
 ```bash
-> wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth src/gfpgan/experiments/pretrained_models/
+> wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth src/gfpgan/experiments/pretrained_models/
 ```
 
 Make sure that you're in the stable-diffusion directory when you do this.
 
-Alternatively, if you have GFPGAN installed elsewhere, or if you are using an earlier version of
+Alternatively, if you have GFPGAN installed elsewhere, or if you are using an
-this package which asked you to install GFPGAN in a sibling directory, you may use the
+earlier version of this package which asked you to install GFPGAN in a sibling
-`--gfpgan_dir` argument with `dream.py` to set a custom path to your GFPGAN directory. _There are
+directory, you may use the `--gfpgan_dir` argument with `dream.py` to set a
-other GFPGAN related boot arguments if you wish to customize further._
+custom path to your GFPGAN directory. _There are other GFPGAN related boot
+arguments if you wish to customize further._
 
 !!! warning "Internet connection needed"
 
@@ -52,13 +57,14 @@ You will now have access to two new prompt arguments.
 
 `-U : <upscaling_factor> <upscaling_strength>`
 
-The upscaling prompt argument takes two values. The first value is a scaling factor and should be
+The upscaling prompt argument takes two values. The first value is a scaling
-set to either `2` or `4` only. This will either scale the image 2x or 4x respectively using
+factor and should be set to either `2` or `4` only. This will either scale the
-different models.
+image 2x or 4x respectively using different models.
 
-You can set the scaling stength between `0` and `1.0` to control intensity of the of the scaling.
+You can set the scaling stength between `0` and `1.0` to control intensity of
-This is handy because AI upscalers generally tend to smooth out texture details. If you wish to
+the of the scaling. This is handy because AI upscalers generally tend to smooth
-retain some of those for natural looking results, we recommend using values between `0.5 to 0.8`.
+out texture details. If you wish to retain some of those for natural looking
+results, we recommend using values between `0.5 to 0.8`.
 
 If you do not explicitly specify an upscaling_strength, it will default to 0.75.
 
@@ -66,18 +72,19 @@ If you do not explicitly specify an upscaling_strength, it will default to 0.75.
 
 `-G : <gfpgan_strength>`
 
-This prompt argument controls the strength of the face restoration that is being applied. Similar to
+This prompt argument controls the strength of the face restoration that is being
-upscaling, values between `0.5 to 0.8` are recommended.
+applied. Similar to upscaling, values between `0.5 to 0.8` are recommended.
 
-You can use either one or both without any conflicts. In cases where you use both, the image will be
+You can use either one or both without any conflicts. In cases where you use
-first upscaled and then the face restoration process will be executed to ensure you get the highest
+both, the image will be first upscaled and then the face restoration process
-quality facial features.
+will be executed to ensure you get the highest quality facial features.
 
 `--save_orig`
 
-When you use either `-U` or `-G`, the final result you get is upscaled or face modified. If you want
+When you use either `-U` or `-G`, the final result you get is upscaled or face
-to save the original Stable Diffusion generation, you can use the `-save_orig` prompt argument to
+modified. If you want to save the original Stable Diffusion generation, you can
-save the original unaffected version too.
+use the `-save_orig` prompt argument to save the original unaffected version
+too.
 
 ### Example Usage
 
@@ -102,60 +109,69 @@ dream> a man wearing a pineapple hat -I path/to/your/file.png -U 2 0.5 -G 0.6
     process is complete. While the image generation is taking place, you will still be able to preview
     the base images.
 
-If you wish to stop during the image generation but want to upscale or face restore a particular
+If you wish to stop during the image generation but want to upscale or face
-generated image, pass it again with the same prompt and generated seed along with the `-U` and `-G`
+restore a particular generated image, pass it again with the same prompt and
-prompt arguments to perform those actions.
+generated seed along with the `-U` and `-G` prompt arguments to perform those
+actions.
 
 ## CodeFormer Support
 
 This repo also allows you to perform face restoration using
 [CodeFormer](https://github.com/sczhou/CodeFormer).
 
-In order to setup CodeFormer to work, you need to download the models like with GFPGAN. You can do
+In order to setup CodeFormer to work, you need to download the models like with
-this either by running `preload_models.py` or by manually downloading the
+GFPGAN. You can do this either by running `preload_models.py` or by manually
-[model file](https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth) and
+downloading the
-saving it to `ldm/restoration/codeformer/weights` folder.
+[model file](https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth)
+and saving it to `ldm/restoration/codeformer/weights` folder.
 
-You can use `-ft` prompt argument to swap between CodeFormer and the default GFPGAN. The above
+You can use `-ft` prompt argument to swap between CodeFormer and the default
-mentioned `-G` prompt argument will allow you to control the strength of the restoration effect.
+GFPGAN. The above mentioned `-G` prompt argument will allow you to control the
+strength of the restoration effect.
 
 ### Usage:
 
-The following command will perform face restoration with CodeFormer instead of the default gfpgan.
+The following command will perform face restoration with CodeFormer instead of
+the default gfpgan.
 
 `<prompt> -G 0.8 -ft codeformer`
 
 ### Other Options:
 
-- `-cf` - cf or CodeFormer Fidelity takes values between `0` and `1`. 0 produces high quality
+- `-cf` - cf or CodeFormer Fidelity takes values between `0` and `1`. 0 produces
-  results but low accuracy and 1 produces lower quality results but higher accuacy to your original
+  high quality results but low accuracy and 1 produces lower quality results but
-  face.
+  higher accuacy to your original face.
 
-The following command will perform face restoration with CodeFormer. CodeFormer will output a result
+The following command will perform face restoration with CodeFormer. CodeFormer
-that is closely matching to the input face.
+will output a result that is closely matching to the input face.
 
 `<prompt> -G 1.0 -ft codeformer -cf 0.9`
 
-The following command will perform face restoration with CodeFormer. CodeFormer will output a result
+The following command will perform face restoration with CodeFormer. CodeFormer
-that is the best restoration possible. This may deviate slightly from the original face. This is an
+will output a result that is the best restoration possible. This may deviate
-excellent option to use in situations when there is very little facial data to work with.
+slightly from the original face. This is an excellent option to use in
+situations when there is very little facial data to work with.
 
 `<prompt> -G 1.0 -ft codeformer -cf 0.1`
 
 ## Fixing Previously-Generated Images
 
-It is easy to apply face restoration and/or upscaling to any previously-generated file. Just use the
+It is easy to apply face restoration and/or upscaling to any
-syntax `!fix path/to/file.png <options>`. For example, to apply GFPGAN at strength 0.8 and upscale 2X
+previously-generated file. Just use the syntax
-for a file named `./outputs/img-samples/000044.2945021133.png`, just run:
+`!fix path/to/file.png <options>`. For example, to apply GFPGAN at strength 0.8
+and upscale 2X for a file named `./outputs/img-samples/000044.2945021133.png`,
+just run:
 
-~~~~
+```
 dream> !fix ./outputs/img-samples/000044.2945021133.png -G 0.8 -U 2
-~~~~
+```
 
-A new file named `000044.2945021133.fixed.png` will be created in the output directory. Note that
+A new file named `000044.2945021133.fixed.png` will be created in the output
-the `!fix` command does not replace the original file, unlike the behavior at generate time.
+directory. Note that the `!fix` command does not replace the original file,
+unlike the behavior at generate time.
 
 ### Disabling:
 
-If, for some reason, you do not wish to load the GFPGAN and/or ESRGAN libraries, you can disable them 
+If, for some reason, you do not wish to load the GFPGAN and/or ESRGAN libraries,
-on the dream.py command line with the `--no_restore` and `--no_upscale` options, respectively.
+you can disable them on the dream.py command line with the `--no_restore` and
+`--no_upscale` options, respectively.

docs/installation/INSTALL_DOCKER.md

@@ -1,15 +1,30 @@
 # Before you begin
 
-- For end users: Install Stable Diffusion locally using the instructions for your OS.
+- For end users: Install Stable Diffusion locally using the instructions for
-- For developers: For container-related development tasks or for enabling easy deployment to other environments (on-premises or cloud), follow these instructions. For general use, install locally to leverage your machine's GPU.
+  your OS.
+- For developers: For container-related development tasks or for enabling easy
+  deployment to other environments (on-premises or cloud), follow these
+  instructions. For general use, install locally to leverage your machine's GPU.
 
 # Why containers?
 
-They provide a flexible, reliable way to build and deploy Stable Diffusion. You'll also use a Docker volume to store the largest model files and image outputs as a first step in decoupling storage and compute. Future enhancements can do this for other assets. See [Processes](https://12factor.net/processes) under the Twelve-Factor App methodology for details on why running applications in such a stateless fashion is important.
+They provide a flexible, reliable way to build and deploy Stable Diffusion.
+You'll also use a Docker volume to store the largest model files and image
+outputs as a first step in decoupling storage and compute. Future enhancements
+can do this for other assets. See [Processes](https://12factor.net/processes)
+under the Twelve-Factor App methodology for details on why running applications
+in such a stateless fashion is important.
 
-You can specify the target platform when building the image and running the container. You'll also need to specify the Stable Diffusion requirements file that matches the container's OS and the architecture it will run on.  
+You can specify the target platform when building the image and running the
+container. You'll also need to specify the Stable Diffusion requirements file
+that matches the container's OS and the architecture it will run on.
 
-Developers on Apple silicon (M1/M2): You [can't access your GPU cores from Docker containers](https://github.com/pytorch/pytorch/issues/81224) and performance is reduced compared with running it directly on macOS but for development purposes it's fine. Once you're done with development tasks on your laptop you can build for the target platform and architecture and deploy to another environment with NVIDIA GPUs on-premises or in the cloud.  
+Developers on Apple silicon (M1/M2): You
+[can't access your GPU cores from Docker containers](https://github.com/pytorch/pytorch/issues/81224)
+and performance is reduced compared with running it directly on macOS but for
+development purposes it's fine. Once you're done with development tasks on your
+laptop you can build for the target platform and architecture and deploy to
+another environment with NVIDIA GPUs on-premises or in the cloud.
 
 # Installation on a Linux container
 
@@ -17,20 +32,29 @@ Developers on Apple silicon (M1/M2): You [can't access your GPU cores from Docke
 
 ### Get the data files
 
-Go to [Hugging Face](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original), and click "Access repository" to Download the model file ```sd-v1-4.ckpt``` (~4 GB) to ```~/Downloads```. You'll need to create an account but it's quick and free.  
+Go to
+[Hugging Face](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original),
+and click "Access repository" to Download the model file `sd-v1-4.ckpt` (~4 GB)
+to `~/Downloads`. You'll need to create an account but it's quick and free.
 
 Also download the face restoration model.
+
 ```Shell
 cd ~/Downloads
-wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth
+wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth
 ```
 
 ### Install [Docker](https://github.com/santisbon/guides#docker)
-On the Docker Desktop app, go to Preferences, Resources, Advanced. Increase the CPUs and Memory to avoid this [Issue](https://github.com/invoke-ai/InvokeAI/issues/342). You may need to increase Swap and Disk image size too.  
+
+On the Docker Desktop app, go to Preferences, Resources, Advanced. Increase the
+CPUs and Memory to avoid this
+[Issue](https://github.com/invoke-ai/InvokeAI/issues/342). You may need to
+increase Swap and Disk image size too.
 
 ## Setup
 
 Set the fork you want to use and other variables.
+
 ```Shell
 TAG_STABLE_DIFFUSION="santisbon/stable-diffusion"
 PLATFORM="linux/arm64"
@@ -46,21 +70,28 @@ echo $CONDA_SUBDIR
 ```
 
 Create a Docker volume for the downloaded model files.
+
 ```Shell
 docker volume create my-vol
 ```
 
-Copy the data files to the Docker volume using a lightweight Linux container. We'll need the models at run time. You just need to create the container with the mountpoint; no need to run this dummy container.
+Copy the data files to the Docker volume using a lightweight Linux container.
+We'll need the models at run time. You just need to create the container with
+the mountpoint; no need to run this dummy container.
+
 ```Shell
 cd ~/Downloads # or wherever you saved the files
 
 docker create --platform $PLATFORM --name dummy --mount source=my-vol,target=/data alpine
 
 docker cp sd-v1-4.ckpt dummy:/data
-docker cp GFPGANv1.3.pth dummy:/data
+docker cp GFPGANv1.4.pth dummy:/data
 ```
 
-Get the repo and download the Miniconda installer (we'll need it at build time). Replace the URL with the version matching your container OS and the architecture it will run on.
+Get the repo and download the Miniconda installer (we'll need it at build time).
+Replace the URL with the version matching your container OS and the architecture
+it will run on.
+
 ```Shell
 cd ~
 git clone $GITHUB_STABLE_DIFFUSION
@@ -70,10 +101,15 @@ chmod +x entrypoint.sh
 wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-aarch64.sh -O anaconda.sh && chmod +x anaconda.sh
 ```
 
-Build the Docker image. Give it any tag ```-t``` that you want.  
+Build the Docker image. Give it any tag `-t` that you want.  
-Choose the Linux container's host platform: x86-64/Intel is ```amd64```. Apple silicon is ```arm64```. If deploying the container to the cloud to leverage powerful GPU instances you'll be on amd64 hardware but if you're just trying this out locally on Apple silicon choose arm64.  
+Choose the Linux container's host platform: x86-64/Intel is `amd64`. Apple
-The application uses libraries that need to match the host environment so use the appropriate requirements file.  
+silicon is `arm64`. If deploying the container to the cloud to leverage powerful
+GPU instances you'll be on amd64 hardware but if you're just trying this out
+locally on Apple silicon choose arm64.  
+The application uses libraries that need to match the host environment so use
+the appropriate requirements file.  
 Tip: Check that your shell session has the env variables set above.
+
 ```Shell
 docker build -t $TAG_STABLE_DIFFUSION \
 --platform $PLATFORM \
@@ -85,6 +121,7 @@ docker build -t $TAG_STABLE_DIFFUSION \
 
 Run a container using your built image.  
 Tip: Make sure you've created and populated the Docker volume (above).
+
 ```Shell
 docker run -it \
 --rm \
@@ -98,26 +135,36 @@ $TAG_STABLE_DIFFUSION
 # Usage (time to have fun)
 
 ## Startup
-If you're on a **Linux container** the ```dream``` script is **automatically started** and the output dir set to the Docker volume you created earlier. 
+
+If you're on a **Linux container** the `dream` script is **automatically
+started** and the output dir set to the Docker volume you created earlier.
 
 If you're **directly on macOS follow these startup instructions**.  
-With the Conda environment activated (```conda activate ldm```), run the interactive interface that combines the functionality of the original scripts ```txt2img``` and ```img2img```:  
+With the Conda environment activated (`conda activate ldm`), run the interactive
-Use the more accurate but VRAM-intensive full precision math because half-precision requires autocast and won't work.  
+interface that combines the functionality of the original scripts `txt2img` and
-By default the images are saved in ```outputs/img-samples/```.
+`img2img`:  
+Use the more accurate but VRAM-intensive full precision math because
+half-precision requires autocast and won't work.  
+By default the images are saved in `outputs/img-samples/`.
+
 ```Shell
 python3 scripts/dream.py --full_precision
 ```
 
 You'll get the script's prompt. You can see available options or quit.
+
 ```Shell
 dream> -h
 dream> q
 ```
 
 ## Text to Image
-For quick (but bad) image results test with 5 steps (default 50) and 1 sample image. This will let you know that everything is set up correctly.  
+
+For quick (but bad) image results test with 5 steps (default 50) and 1 sample
+image. This will let you know that everything is set up correctly.  
 Then increase steps to 100 or more for good (but slower) results.  
 The prompt can be in quotes or not.
+
 ```Shell
 dream> The hulk fighting with sheldon cooper -s5 -n1
 dream> "woman closeup highly detailed"  -s 150
@@ -125,45 +172,68 @@ dream> "woman closeup highly detailed"  -s 150
 dream> "woman closeup highly detailed"  --steps 150 --seed -1 -G 0.75
 ```
 
-You'll need to experiment to see if face restoration is making it better or worse for your specific prompt.
+You'll need to experiment to see if face restoration is making it better or
+worse for your specific prompt.
 
-If you're on a container the output is set to the Docker volume. You can copy it wherever you want.  
+If you're on a container the output is set to the Docker volume. You can copy it
+wherever you want.  
 You can download it from the Docker Desktop app, Volumes, my-vol, data.  
-Or you can copy it from your Mac terminal. Keep in mind ```docker cp``` can't expand ```*.png``` so you'll need to specify the image file name.  
+Or you can copy it from your Mac terminal. Keep in mind `docker cp` can't expand
+`*.png` so you'll need to specify the image file name.
+
+On your host Mac (you can use the name of any container that mounted the
+volume):
 
-On your host Mac (you can use the name of any container that mounted the volume):
 ```Shell
 docker cp dummy:/data/000001.928403745.png /Users/<your-user>/Pictures
 ```
 
 ## Image to Image
-You can also do text-guided image-to-image translation. For example, turning a sketch into a detailed drawing.  
 
-```strength``` is a value between 0.0 and 1.0 that controls the amount of noise that is added to the input image. Values that approach 1.0 allow for lots of variations but will also produce images that are not semantically consistent with the input. 0.0 preserves image exactly, 1.0 replaces it completely.  
+You can also do text-guided image-to-image translation. For example, turning a
+sketch into a detailed drawing.
 
-Make sure your input image size dimensions are multiples of 64 e.g. 512x512. Otherwise you'll get ```Error: product of dimension sizes > 2**31'```. If you still get the error [try a different size](https://support.apple.com/guide/preview/resize-rotate-or-flip-an-image-prvw2015/mac#:~:text=image's%20file%20size-,In%20the%20Preview%20app%20on%20your%20Mac%2C%20open%20the%20file,is%20shown%20at%20the%20bottom.) like 512x256.  
+`strength` is a value between 0.0 and 1.0 that controls the amount of noise that
+is added to the input image. Values that approach 1.0 allow for lots of
+variations but will also produce images that are not semantically consistent
+with the input. 0.0 preserves image exactly, 1.0 replaces it completely.
+
+Make sure your input image size dimensions are multiples of 64 e.g. 512x512.
+Otherwise you'll get `Error: product of dimension sizes > 2**31'`. If you still
+get the error
+[try a different size](https://support.apple.com/guide/preview/resize-rotate-or-flip-an-image-prvw2015/mac#:~:text=image's%20file%20size-,In%20the%20Preview%20app%20on%20your%20Mac%2C%20open%20the%20file,is%20shown%20at%20the%20bottom.)
+like 512x256.
 
 If you're on a Docker container, copy your input image into the Docker volume
+
 ```Shell
 docker cp /Users/<your-user>/Pictures/sketch-mountains-input.jpg dummy:/data/
 ```
 
-Try it out generating an image (or more). The ```dream``` script needs absolute paths to find the image so don't use ```~```.  
+Try it out generating an image (or more). The `dream` script needs absolute
+paths to find the image so don't use `~`.
 
 If you're on your Mac
+
 ```Shell
 dream> "A fantasy landscape, trending on artstation" -I /Users/<your-user>/Pictures/sketch-mountains-input.jpg --strength 0.75  --steps 100 -n4
 ```
+
 If you're on a Linux container on your Mac
+
 ```Shell
 dream> "A fantasy landscape, trending on artstation" -I /data/sketch-mountains-input.jpg --strength 0.75  --steps 50 -n1
 ```
 
 ## Web Interface
-You can use the ```dream``` script with a graphical web interface. Start the web server with:
+
+You can use the `dream` script with a graphical web interface. Start the web
+server with:
+
 ```Shell
 python3 scripts/dream.py --full_precision --web
 ```
+
 If it's running on your Mac point your Mac web browser to http://127.0.0.1:9090
 
 Press Control-C at the command line to stop the web server.
@@ -171,11 +241,13 @@ Press Control-C at the command line to stop the web server.
 ## Notes
 
 Some text you can add at the end of the prompt to make it very pretty:
+
 ```Shell
 cinematic photo, highly detailed, cinematic lighting, ultra-detailed, ultrarealistic, photorealism, Octane Rendering, cyberpunk lights, Hyper Detail, 8K, HD, Unreal Engine, V-Ray, full hd, cyberpunk, abstract, 3d octane render + 4k UHD + immense detail + dramatic lighting + well lit + black, purple, blue, pink, cerulean, teal, metallic colours, + fine details, ultra photoreal, photographic, concept art, cinematic composition, rule of thirds, mysterious, eerie, photorealism, breathtaking detailed, painting art deco pattern, by hsiao, ron cheng, john james audubon, bizarre compositions, exquisite detail, extremely moody lighting, painted by greg rutkowski makoto shinkai takashi takeuchi studio ghibli, akihiko yoshida
 ```
 
 The original scripts should work as well.
+
 ```Shell
 python3 scripts/orig_scripts/txt2img.py --help
 python3 scripts/orig_scripts/txt2img.py --ddim_steps 100 --n_iter 1 --n_samples 1  --plms --prompt "new born baby kitten. Hyper Detail, Octane Rendering, Unreal Engine, V-Ray"

ldm/dream/args.py

@@ -400,7 +400,7 @@ class Args(object):
         postprocessing_group.add_argument(
             '--gfpgan_model_path',
             type=str,
-            default='experiments/pretrained_models/GFPGANv1.3.pth',
+            default='experiments/pretrained_models/GFPGANv1.4.pth',
             help='Indicates the path to the GFPGAN model, relative to --gfpgan_dir.',
         )
         postprocessing_group.add_argument(

ldm/dream/restoration/base.py

@@ -2,7 +2,7 @@ class Restoration():
     def __init__(self) -> None:
         pass
 
-    def load_face_restore_models(self, gfpgan_dir='./src/gfpgan', gfpgan_model_path='experiments/pretrained_models/GFPGANv1.3.pth'):
+    def load_face_restore_models(self, gfpgan_dir='./src/gfpgan', gfpgan_model_path='experiments/pretrained_models/GFPGANv1.4.pth'):
         # Load GFPGAN
         gfpgan = self.load_gfpgan(gfpgan_dir, gfpgan_model_path)
         if gfpgan.gfpgan_model_exists:

ldm/dream/restoration/gfpgan.py

@@ -11,7 +11,7 @@ class GFPGAN():
     def __init__(
             self,
             gfpgan_dir='src/gfpgan',
-            gfpgan_model_path='experiments/pretrained_models/GFPGANv1.3.pth') -> None:
+            gfpgan_model_path='experiments/pretrained_models/GFPGANv1.4.pth') -> None:
 
         self.model_path = os.path.join(gfpgan_dir, gfpgan_model_path)
         self.gfpgan_model_exists = os.path.isfile(self.model_path)
@@ -50,7 +50,7 @@ class GFPGAN():
                 f'>> WARNING: GFPGAN not initialized.'
             )
             print(
-                f'>> Download https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth to {self.model_path}, \nor change GFPGAN directory with --gfpgan_dir.'
+                f'>> Download https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth to {self.model_path}, \nor change GFPGAN directory with --gfpgan_dir.'
             )
 
         image = image.convert('RGB')

scripts/preload_models.py

@@ -87,8 +87,8 @@ if gfpgan:
 
     try:
         import urllib.request
-        model_url  = 'https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth'
+        model_url  = 'https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth'
-        model_dest = 'src/gfpgan/experiments/pretrained_models/GFPGANv1.3.pth'
+        model_dest = 'src/gfpgan/experiments/pretrained_models/GFPGANv1.4.pth'
 
         if not os.path.exists(model_dest):
             print('downloading gfpgan model file...')